README.md

metadata

license: apache-2.0
base_model: bedus-creation/mBart-small-dataset-i-eng-lim
tags:
  - generated_from_keras_callback
model-index:
  - name: bedus-creation/mBart-small-dataset-ii-eng-lim-004
    results: []

bedus-creation/mBart-small-dataset-ii-eng-lim-004

This model is a fine-tuned version of bedus-creation/mBart-small-dataset-i-eng-lim on an unknown dataset. It achieves the following results on the evaluation set:

• Train Loss: 0.2275
• Validation Loss: 0.3200
• Epoch: 74

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• optimizer: {'name': 'AdamWeightDecay', 'learning_rate': 1e-04, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01}
• training_precision: float32

Training results

Train Loss	Validation Loss	Epoch
0.9940	0.4653	0
0.4659	0.3647	1
0.4011	0.3331	2
0.3798	0.3284	3
0.3640	0.3210	4
0.3539	0.3087	5
0.3456	0.3106	6
0.3377	0.3049	7
0.3340	0.2998	8
0.3285	0.2974	9
0.3246	0.2980	10
0.3202	0.2950	11
0.3174	0.2910	12
0.3154	0.2932	13
0.3124	0.2882	14
0.3094	0.2895	15
0.3092	0.2880	16
0.3073	0.2861	17
0.3043	0.2842	18
0.3037	0.2856	19
0.3009	0.2834	20
0.2999	0.2859	21
0.2983	0.2836	22
0.2973	0.2809	23
0.2952	0.2825	24
0.2942	0.2809	25
0.2933	0.2792	26
0.2914	0.2813	27
0.2898	0.2817	28
0.2884	0.2794	29
0.2866	0.2797	30
0.2853	0.2797	31
0.2849	0.2844	32
0.2835	0.2798	33
0.2821	0.2803	34
0.2823	0.2828	35
0.2798	0.2796	36
0.2797	0.2788	37
0.2766	0.2811	38
0.2765	0.2800	39
0.2747	0.2852	40
0.2731	0.2825	41
0.2720	0.2841	42
0.2709	0.2855	43
0.2693	0.2843	44
0.2678	0.2863	45
0.2667	0.2912	46
0.2645	0.2863	47
0.2633	0.2862	48
0.2618	0.2881	49
0.2607	0.2890	50
0.2585	0.2928	51
0.2585	0.2903	52
0.2562	0.2904	53
0.2545	0.2902	54
0.2541	0.2937	55
0.2528	0.2930	56
0.2512	0.3014	57
0.2484	0.2979	58
0.2478	0.3002	59
0.2460	0.3034	60
0.2449	0.3000	61
0.2442	0.3010	62
0.2418	0.3054	63
0.2399	0.3046	64
0.2395	0.3072	65
0.2374	0.3117	66
0.2368	0.3081	67
0.2351	0.3149	68
0.2334	0.3155	69
0.2335	0.3123	70
0.2310	0.3193	71
0.2296	0.3169	72
0.2277	0.3220	73
0.2275	0.3200	74

Framework versions

• Transformers 4.33.3
• TensorFlow 2.13.0
• Datasets 2.14.5
• Tokenizers 0.13.3